Related papers: Learning from Mistakes: Self-correct Adversarial T…

We investigate the learning task of language generation in the limit, but shift focus from the traditional time-of-last-mistake metric of a generator's success to a new notion of "mistake-bounded generation." While existing results for…

While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk is emerging: capability-oriented training induced exploitation. We investigate whether language models, when…

Machine learning is a tool for building models that accurately represent input training data. When undesired biases concerning demographic groups are in the training data, well-trained models will reflect those biases. We present a…

Diffusion models (DMs) have achieved remarkable success in text-to-image generation, but they also pose safety risks, such as the potential generation of harmful content and copyright violations. The techniques of machine unlearning, also…

The rise of deep learning technique has raised new privacy concerns about the training data and test data. In this work, we investigate the model inversion problem in the adversarial settings, where the adversary aims at inferring…

Machine-learning models can be fooled by adversarial examples, i.e., carefully-crafted input perturbations that force models to output wrong predictions. While uncertainty quantification has been recently proposed to detect adversarial…

Recent work has shown the importance of adaptation of broad-coverage contextualised embedding models on the domain of the target task of interest. Current self-supervised adaptation methods are simplistic, as the training signal comes from…

Recently, substantial progress has been made in language modeling by using deep neural networks. However, in practice, large scale neural language models have been shown to be prone to overfitting. In this paper, we present a simple yet…

Editing human-written text has become a standard use case of large language models (LLMs), for example, to make one's arguments more appropriate for a discussion. Comparing human to LLM-generated edits, however, we observe a mismatch in…

Machine Learning models face increased concerns regarding the storage of personal user data and adverse impacts of corrupted data like backdoors or systematic bias. Machine Unlearning can address these by allowing post-hoc deletion of…

Adversarial attacks on machine learning algorithms have been a key deterrent to the adoption of AI in many real-world use cases. They significantly undermine the ability of high-performance neural networks by forcing misclassifications.…

Although large language models (LLMs) have transformed AI, they still make mistakes and can explore unproductive reasoning paths. Self-correction capability is essential for deploying LLMs in safety-critical applications. We uncover a…

Predicting the trajectories of surrounding objects is a critical task for self-driving vehicles and many other autonomous systems. Recent works demonstrate that adversarial attacks on trajectory prediction, where small crafted perturbations…

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

When trained on large, unfiltered crawls from the internet, language models pick up and reproduce all kinds of undesirable biases that can be found in the data: they often generate racist, sexist, violent or otherwise toxic language. As…

Chinese word usage errors often occur in non-native Chinese learners' writing. It is very helpful for non-native Chinese learners to detect them automatically when learning writing. In this paper, we propose a novel approach, which takes…

Understanding the vulnerability of large-scale pre-trained vision-language models like CLIP against adversarial attacks is key to ensuring zero-shot generalization capacity on various downstream tasks. State-of-the-art defense mechanisms…

The massive amounts of web-mined parallel data contain large amounts of noise. Semantic misalignment, as the primary source of the noise, poses a challenge for training machine translation systems. In this paper, we first introduce a…

Adversarial attacks in texts are mostly substitution-based methods that replace words or characters in the original texts to achieve success attacks. Recent methods use pre-trained language models as the substitutes generator. While in…

Chinese word segmentation is especially fragile in non-standard text, where language learner errors and other character-level divergences disrupt the word boundaries assumed by downstream annotation and evaluation. This paper formulates…